© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68597
    Prev
    Next
    INDEX
    Explanations

    organizational units and subdivisions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     avancer
    -1.45
     finanzi
    -1.38
    魮
    -1.36
     合集
    -1.36
     emporio
    -1.36
    lijst
    -1.35
     [\
    -1.34
     gekle
    -1.30
     статистики
    -1.28
     髪型
    -1.28
    POSITIVE LOGITS
     of
    2.41
    ༛
    1.46
     arid
    1.44
     T
    1.38
     unplanned
    1.34
     revel
    1.33
    五百
    1.33
     =
    1.32
     Mal
    1.32
     like
    1.28
    Activations Density 0.028%

    No Known Activations